© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 30446
    Prev
    Next
    INDEX
    Explanations

    hours and minutes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Glob
    -0.07
     Conrad
    -0.07
    ount
    -0.06
     dated
    -0.06
     typ
    -0.06
     Pepsi
    -0.06
     Alv
    -0.06
     Roma
    -0.06
     seated
    -0.05
    395
    -0.05
    POSITIVE LOGITS
    owski
    0.13
     jsx
    0.12
     Bout
    0.12
     rejuven
    0.12
     recur
    0.12
    opts
    0.12
    >↵↵↵↵↵
    0.12
    StyleSheet
    0.12
     Hayward
    0.12
     carve
    0.11
    Activations Density 0.003%

    No Known Activations